A browser agent that finds flights in seven seconds. A Claude session cut from a million tokens to 86,000 in one second. A WHERE clause that reads plain English. Vercel's safety reviewer. We are collecting what people built with Jev in its first days, and what they argued about, each in their own words. Nobody in these bylines is on eChai, and every entry links back to where it was posted.
13 entries Clear
Chris Tate, of Vercel, on json-render with Jev deciding the tree: generative UI rendered in milliseconds from your own components and design system. Guillermo Rauch's reply was that Jev generative UI had been achieved externally.
Chris Tate
3h
New experiment: json-render + jev
The future Generative UI is instant
Your components, your actions, your design system
Rendered in milliseconds
Nader Dabit's third: intent-based search over a Gmail inbox, with his own caveat that on a very large inbox you would let embeddings pull first.
Nader Dabit
7h
Jev is really good at intent-based search!
How it looks in Gmail:
(for a huge inbox you'd prob let semantic search / embeddings pull first but still much better experience)
Kitze, with a calculator notebook that takes plain-language terms.
Kitze
13h
i made a smart calculator notebook using jev
it can calculate ANYTHING!! 😅
Tony Dinh's Chrome extension listens to a YouTube video, has Jev decide in real time whether a sponsor segment has started, and skips it, at about half a cent a video. Bring your own key; the code is open.
Tony Dinh
18h
Just trying out Jev, I made a Chrome extension that:
- Listens to your YouTube audio (optional)
- Detects if it gets to a sponsor segment
- Skips it ➡️➡️➡️
- All in real-time while costing ~$0.005 per video
Prototype project, BYOK, open-source:
Nader Dabit's second: type a column head like 'Urgency' and every row fills in as you type, about 100 ms each. A spreadsheet that recalculates meaning rather than numbers.
Nader Dabit
19h
Another crazy @typesafeai Jev example:
Predictive spreadsheets
Spreadsheets recalculate numbers, not meaning. Jev reads intent.
Type "Urgency" at the top of a column and, as you type, it figures out you want each row rated from "no follow-up needed" to "urgent" in ~100 ms.
Nader Dabit, with the first of his experiments. A launcher usually ranks by alias, fuzzy match and habit; this one reads intent, so typing 'the pdf I just downloaded' puts the newest PDF at the top, with a confidence on every keystroke, in about 100 ms.
Nader Dabit
21h
Also have been playing with @typesafeai Jev, insane!
So many immediate use cases and new apps are possible. What a time to be a builder!
Sharing some experiments here starting with:
Keystroke oracle / predictive launcher:
Your launcher ranks by aliases, fuzzy match, and habit.
Jev reads intent: type "the pdf I just downloaded" and the newest PDF is already the top hit with a full confidence on every keystroke, in ~100 ms
Jack Cheng's post is three words and the film is the point: a canvas you draw on by pointing and speaking, with Jev turning the gesture and the words into the drawing action.
Jack Cheng
23h
Jev is the future
Zachi's jev() is the entry on this page that most changes what a piece of software can be: a PostgreSQL function that takes a row and a plain-English question and returns whether it holds, so a WHERE clause can read 'could work from home'. No index and no embeddings; 129 rows judged in about a second for $0.0009, and a cached second run in 6 ms.
Zachi
1d
I think I just cooked something 🔥
jev(): a PostgreSQL extension that searches your whole database in natural language. No index, no embeddings, just one function.
WHERE jev(people, 'could work from home')
or
WHERE jev(people, 'name sounds european')
129 rows judged in ~1s for $0.0009. Second run: 6ms from cache.
CJ, of Coding Garden, built a chat bot with no language model in it at all. Jev picks the tool (web search, Wikipedia, weather, Todoist, Home Assistant) and its arguments from the prompt, the tool answers, and the answer cites its source. The film runs over four minutes, so it plays where it was posted.
CJ (Coding Garden)
1d
I built a chat bot with jev, no LLM at all! Responses are instant, no hallucinations.
I hooked it up to web search, wikipedia, weather, todoist and home assistant.
Jev decides what tool to call and what args to use based on the prompt. Instant answers cite sources as well!
Zachi's other one, from earlier the same day: an ad blocker that asks Jev about every element on the page rather than matching a list, so there is nothing for an advertiser's markup to dodge.
Zachi
1d
I build an undetectable realtime adblocker extension with typesafe
It checks every dom element and classifies as ad/non-ad and removes it if true
Extremely fun to work with, expecting an incredible shift in how AI is being used in the future
Ilias Ism runs several small products and had accumulated the regex that AI-assisted coding leaves behind. He is moving those rules to Jev calls across aiseotracker, linkdr and genppt, and says that where it replaces an ordinary LLM call it is around ten times faster and half the price.
Ilias Ism
1d
Now using @typesafeai Jev in http://aiseotracker.com, http://linkdr.com, http://genppt.com, etc
AI ends up vibe coding so much AI regex slop if you don't read the code, so I can finally move all this hard-coding to Jev and it's insanely fast!
Also for regular LLM calls, it is around 10x faster, 50% cheaper
Xuanwo, of LanceDB, with a semantic lens: a near-real-time filter over a dataset in plain language, no features defined in advance. The demo is live at the link.
Xuanwo
1d
Built a cool semantic lens based on @typesafeai's Jev and @lancedb.
Now, we can do semancti filter nearly realtime, no need to predefine features anymore. Just search and explore!
Here is the demo: https://semanticlens.xuanwo.io/
Have fun!
Steve Krouse is the founder of Val Town. His demo, TypeSafe Typewriter, is live at the link and built on Val Town.
Steve Krouse
2d
typesafe's jev is fun! live demo you can play with:
